四十二：基于同行排序共识的群体推理

摘要

随着集中式AI触及算力瓶颈且大规模训练带来的边际效益递减，满足需求需要一个在容量与能力上均可横向扩展的推理层。本文提出Fortytwo协议——一种基于群体智能原理与分布式两两排序共识的新型协议，可在AI推理中实现卓越性能。我们的方法通过"群体推理"重构AI节点间的协作机制：利用异构模型间的同行评分、声誉加权共识来筛选最优响应。采用自定义布拉德利-特里模型进行两两排序的结果表明，群体推理显著优于多数投票法，在GPQA Diamond基准上达到85.90%准确率，相较同等模型集下多数投票法的68.69%提升17.21个百分点（相对提升约25.1%）。该协议引入链上声誉机制，使节点影响力随实际准确率动态调整，形成优胜劣汰的共识体系以过滤低质量或恶意参与者。为抵御女巫攻击，Fortytwo在共识中采用能力证明机制：节点需成功完成校准/测试请求并质押声誉值才能进入排序环节，在保持开放性的同时使多身份攻击无利可图。在GPQA Diamond、LiveCodeBench和AIME等六项挑战性基准测试中，我们的方案展现出更高准确率及对对抗性/噪声自由提示的强大鲁棒性（例如提示注入攻击下的性能衰减仅0.12%，而单体单模型基线为6.20%），同时保持实际可部署性。这些成果为去中心化AI系统奠定基础，通过集体智能实现高质量推理的民主化接入，且无需牺牲可靠性或安全性。

English

As centralized AI hits compute ceilings and diminishing returns from ever-larger training runs, meeting demand requires an inference layer that scales horizontally in both capacity and capability. We present Fortytwo, a novel protocol that leverages swarm intelligence principles and distributed pairwise ranking consensus to achieve superior performance in AI inference. Our approach reimagines collaboration among AI nodes using swarm inference: a peer-ranked, reputation-weighted consensus across heterogeneous models that surfaces the highest-quality responses. Using pairwise ranking with a custom Bradley-Terry-style aggregation model, we demonstrate that swarm inference substantially outperforms majority voting, achieving 85.90% on GPQA Diamond versus 68.69% for majority voting with the same model set - an improvement of +17.21 percentage points (approximately +25.1% relative). The protocol incorporates on-chain reputation so node influence adapts to demonstrated accuracy over time, yielding a meritocratic consensus that filters low-quality or malicious participants. To resist Sybil attacks, Fortytwo employs proof-of-capability in its consensus: nodes must successfully complete calibration/test requests and stake reputation to enter ranking rounds, making multi-identity attacks economically unattractive while preserving openness. Across six challenging benchmarks, including GPQA Diamond, LiveCodeBench, and AIME, our evaluation indicates higher accuracy and strong resilience to adversarial and noisy free-form prompting (e.g., prompt-injection degradation of only 0.12% versus 6.20% for a monolithic single-model baseline), while retaining practical deployability. Together, these results establish a foundation for decentralized AI systems - democratizing access to high-quality inference through collective intelligence without sacrificing reliability or security.

四十二：基于同行排序共识的群体推理

Fortytwo: Swarm Inference with Peer-Ranked Consensus

摘要

Support